arXiv subjects

Jiahui Lin

Publications and source records attributed to Jiahui Lin.

6 recordsLinked to original sources

arXiv2026

AI-Driven Discovery of Information-Efficient Collider Observables for Interference Measurements

Optimal observables provide statistically powerful probes of small deformations from a reference theory, but in realistic collider measurements they are rarely available in compact analytic form. We show that interpretable event-level observables can be discovered by AI-driven symbolic evolution using score information from matrix-element reweighting as the statistical target. Focusing on the CP-sensitive interaction $HZ_{\mu\nu}\tilde Z^{\mu\nu}$, we study two complementary realizations of the same coupling structure: associated production $e^+e^-\to Z(\to \mu^-\mu^+)H$ and the decay channel $pp\to H\to ZZ^*\to e^-e^+\mu^-\mu^+$. The learned observables retain substantially more local Fisher information than standard angular baselines while remaining compact analytic functions. In both cases, the discovered expressions recover characteristic helicity-interference harmonics. In associated production these harmonics are supplemented by laboratory-frame asymmetry mappings, while in four-lepton decay the robust component is the angular kernel, with the mass-ratio factor serving as a bounded representative prefactor. These results recast optimal-observable design as a symbolic discovery problem and provide a transparent route to information-efficient, interpretable probes of collider interference.

hep-ph↗

arXiv2026

GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents

We present GLM-5V-Turbo, a step toward native foundation models for multimodal agents. As foundation models are increasingly deployed in real environments, agentic capability depends not only on language reasoning, but also on the ability to perceive, interpret, and act over heterogeneous contexts such as images, videos, webpages, documents, GUIs. GLM-5V-Turbo is built around this objective: multimodal perception is integrated as a core component of reasoning, planning, tool use, and execution, rather than as an auxiliary interface to a language model. This report summarizes the main improvements behind GLM-5V-Turbo across model design, multimodal training, reinforcement learning, toolchain expansion, and integration with agent frameworks. These developments lead to strong performance in multimodal coding, visual tool use, and framework-based agentic tasks, while preserving competitive text-only coding capability. More importantly, our development process offers practical insights for building multimodal agents, highlighting the central role of multimodal perception, hierarchical optimization, and reliable end-to-end verification.

cs.CV↗

arXiv2026

Can Deep Research Agents Retrieve and Organize? Evaluating the Synthesis Gap with Expert Taxonomies

Deep Research Agents increasingly automate survey writing, yet existing benchmarks do not jointly test whether they retrieve the papers experts consider essential and organize those papers into paper-grounded taxonomies. We introduce TaxoBench, a benchmark built from 72 highly cited LLM surveys, 3,815 cited papers, and their expert-authored taxonomies. TaxoBench evaluates systems in two settings: Deep Research mode measures end-to-end retrieval and organization from a topic, while Bottom-Up mode provides the expert paper set and isolates organization. We evaluate leaf-level assignments with ARI and V-Measure and hierarchy-level structure with US-TED, US-NTED, and Sem-Path. Across 7 Deep Research Agents and 16 LLM configurations, the best agent retrieves only 20.92% of expert-cited papers, and none of 70 standard Bottom-Up runs reaches the experts' average depth of 4.86. A controlled probe shows that models which match this depth do so by fragmenting the taxonomy, reducing alignment with the expert reference. We further find that raw Sem-Path remains near a no-organization floor even when a newer model generation gains 3.68 pp ARI; after depth matching, humans lead on all 10 matched surveys by 13.27 pp. These results identify retrieval and hierarchical organization as separate bottlenecks and show why hierarchy metrics must be calibrated before they are used to compare models.

cs.CL↗

arXiv2020

Search-Based Online Trajectory Planning for Car-like Robots in Highly Dynamic Environments

This paper presents a search-based partial motion planner to generate dynamically feasible trajectories for car-like robots in highly dynamic environments. The planner searches for smooth, safe, and near-time-optimal trajectories by exploring a state graph built on motion primitives, which are generated by discretizing the time dimension and the control space. To enable fast online planning, we first propose an efficient path searching algorithm based on the aggregation and pruning of motion primitives. We then propose a fast collision checking algorithm that takes into account the motions of moving obstacles. The algorithm linearizes relative motions between the robot and obstacles and then checks collisions by comparing a point-line distance. Benefiting from the fast searching and collision checking algorithms, the planner can effectively and safely explore the state-time space to generate near-time-optimal solutions. The results through extensive experiments show that the proposed method can generate feasible trajectories within milliseconds while maintaining a higher success rate than up-to-date methods, which significantly demonstrates its advantages.

cs.RO↗

arXiv2020

Online State-Time Trajectory Planning Using Timed-ESDF in Highly Dynamic Environments

Online state-time trajectory planning in highly dynamic environments remains an unsolved problem due to the unpredictable motions of moving obstacles and the curse of dimensionality from the state-time space. Existing state-time planners are typically implemented based on randomized sampling approaches or path searching on discretized state graph. The smoothness, path clearance, and planning efficiency of these planners are usually not satisfying. In this work, we propose a gradient-based planner over the state-time space for online trajectory generation in highly dynamic environments. To enable the gradient-based optimization, we propose a Timed-ESDT that supports distance and gradient queries with state-time keys. Based on the Timed-ESDT, we also define a smooth prior and an obstacle likelihood function that is compatible with the state-time space. The trajectory planning is then formulated to a MAP problem and solved by an efficient numerical optimizer. Moreover, to improve the optimality of the planner, we also define a state-time graph and then conduct path searching on it to find a better initialization for the optimizer. By integrating the graph searching, the planning quality is significantly improved. Experiment results on simulated and benchmark datasets show that our planner can outperform the state-of-the-art methods, demonstrating its significant advantages over the traditional ones.

cs.RO↗

arXiv2020

How initial distribution affects symmetry breaking induced by panic in ants: experiment and flee-pheromone model

Collective escaping is a ubiquitous phenomenon in animal groups. Symmetry breaking caused by panic escape exhibits a shared feature across species that one exit is used more than the other when agents escaping from a closed space with two symmetrically located exists. Intuitively, one exit will be used more by more individuals close to it, namely there is an asymmetric distribution initially. We used ant groups to investigate how initial distribution of colonies would influence symmetry breaking in collective escaping. Surprisingly, there was no positive correlation between symmetry breaking and the asymmetrically initial distribution, which was quite counter-intuitive. In the experiments, a flee stage was observed and accordingly a flee-pheromone model was introduced to depict this special behavior in the early stage of escaping. Simulation results fitted well with the experiment. Furthermore, the flee stage duration was calibrated quantitatively and the model reproduced the observation demonstrated by our previous work. This paper explicitly distinguished two stages in ant panic escaping for the first time, thus enhancing the understanding in escaping behavior of ant colonies.

q-bio.QM↗